Instructions to use microsoft/trocr-large-handwritten with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/trocr-large-handwritten with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="microsoft/trocr-large-handwritten")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("microsoft/trocr-large-handwritten") model = AutoModelForImageTextToText.from_pretrained("microsoft/trocr-large-handwritten") - Notebooks
- Google Colab
- Kaggle
ValueError: decoder_start_token_id....
#7
by Ruzwaahn - opened
Hi I've downloaded all files and have run the following code:
processor = TrOCRProcessir.from_pretrained('./', local_files_only=True)
Model= VisionEncoderDecoderModel.from_pretrained('./', local_files_only=True)
image = image.open("...")
pixel_values = processor(images=image, return_tensors="pt").pixel_values
generated_ids = model.generate(pixel_values)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
And I'm getting the following error:
ValueError: 'decoder_start_token_id' or 'bos_token_id' has to be defined for encoder-decoder generation.